|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SnowballTarget.Policy.Entropy.mean": { |
|
"value": 1.0066413879394531, |
|
"min": 1.0066413879394531, |
|
"max": 2.854454517364502, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Entropy.sum": { |
|
"value": 9611.412109375, |
|
"min": 9611.412109375, |
|
"max": 29232.46875, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.mean": { |
|
"value": 199984.0, |
|
"min": 9952.0, |
|
"max": 199984.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Step.sum": { |
|
"value": 199984.0, |
|
"min": 9952.0, |
|
"max": 199984.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 13.193480491638184, |
|
"min": 0.403181791305542, |
|
"max": 13.193480491638184, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 2572.728759765625, |
|
"min": 78.21726989746094, |
|
"max": 2684.68359375, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.mean": { |
|
"value": 199.0, |
|
"min": 199.0, |
|
"max": 199.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.EpisodeLength.sum": { |
|
"value": 8756.0, |
|
"min": 8756.0, |
|
"max": 10945.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.mean": { |
|
"value": 0.0704354401836206, |
|
"min": 0.06285314128870274, |
|
"max": 0.07284147253117493, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.PolicyLoss.sum": { |
|
"value": 0.2817417607344824, |
|
"min": 0.251412565154811, |
|
"max": 0.35684781057252796, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.mean": { |
|
"value": 0.17840444208944545, |
|
"min": 0.12763487225781905, |
|
"max": 0.2773823547889204, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Losses.ValueLoss.sum": { |
|
"value": 0.7136177683577818, |
|
"min": 0.5105394890312762, |
|
"max": 1.3869117739446022, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.mean": { |
|
"value": 8.082097306000007e-06, |
|
"min": 8.082097306000007e-06, |
|
"max": 0.000291882002706, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.LearningRate.sum": { |
|
"value": 3.232838922400003e-05, |
|
"min": 3.232838922400003e-05, |
|
"max": 0.00138516003828, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.mean": { |
|
"value": 0.10269399999999997, |
|
"min": 0.10269399999999997, |
|
"max": 0.19729400000000002, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Epsilon.sum": { |
|
"value": 0.41077599999999986, |
|
"min": 0.41077599999999986, |
|
"max": 0.9617200000000001, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Beta.mean": { |
|
"value": 0.0001444306000000001, |
|
"min": 0.0001444306000000001, |
|
"max": 0.004864970599999999, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.Beta.sum": { |
|
"value": 0.0005777224000000004, |
|
"min": 0.0005777224000000004, |
|
"max": 0.023089828000000003, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.mean": { |
|
"value": 25.704545454545453, |
|
"min": 4.0, |
|
"max": 26.204545454545453, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Environment.CumulativeReward.sum": { |
|
"value": 1131.0, |
|
"min": 176.0, |
|
"max": 1426.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.mean": { |
|
"value": 25.704545454545453, |
|
"min": 4.0, |
|
"max": 26.204545454545453, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.Policy.ExtrinsicReward.sum": { |
|
"value": 1131.0, |
|
"min": 176.0, |
|
"max": 1426.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
}, |
|
"SnowballTarget.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1674567885", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1674568397" |
|
}, |
|
"total": 512.167365348, |
|
"count": 1, |
|
"self": 0.43202563700003793, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1027309859999832, |
|
"count": 1, |
|
"self": 0.1027309859999832 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 511.63260872499995, |
|
"count": 1, |
|
"self": 0.5439965729986511, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.397954602000027, |
|
"count": 1, |
|
"self": 9.397954602000027 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 501.5470259190012, |
|
"count": 18201, |
|
"self": 0.30683677400310216, |
|
"children": { |
|
"env_step": { |
|
"total": 501.2401891449981, |
|
"count": 18201, |
|
"self": 355.21946946900323, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 145.74616997299336, |
|
"count": 18201, |
|
"self": 1.4357976350008244, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 144.31037233799253, |
|
"count": 18201, |
|
"self": 33.013960455987615, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 111.29641188200492, |
|
"count": 18201, |
|
"self": 111.29641188200492 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.2745497030015258, |
|
"count": 18201, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 510.37723168699193, |
|
"count": 18201, |
|
"is_parallel": true, |
|
"self": 288.0555822959864, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005986983000013879, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0036540049999302937, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0023329780000835854, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0023329780000835854 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04431484900004534, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004771840000330485, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00027200799996762726, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00027200799996762726 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.042281454000033136, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.042281454000033136 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.00128420300001153, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045128199997179763, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008329210000397325, |
|
"count": 10, |
|
"is_parallel": true, |
|
"self": 0.0008329210000397325 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 222.3216493910055, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 8.404275422994772, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 4.89171866199564, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 4.89171866199564 |
|
}, |
|
"communicator.exchange": { |
|
"total": 179.6284053080135, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 179.6284053080135 |
|
}, |
|
"steps_from_proto": { |
|
"total": 29.397249998001598, |
|
"count": 18200, |
|
"is_parallel": true, |
|
"self": 6.395638867017567, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 23.00161113098403, |
|
"count": 182000, |
|
"is_parallel": true, |
|
"self": 23.00161113098403 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 4.1142999975818384e-05, |
|
"count": 1, |
|
"self": 4.1142999975818384e-05, |
|
"children": { |
|
"thread_root": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"trainer_advance": { |
|
"total": 498.62786561201176, |
|
"count": 349478, |
|
"is_parallel": true, |
|
"self": 9.161158002999969, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 241.48621794601206, |
|
"count": 349478, |
|
"is_parallel": true, |
|
"self": 240.64110423801208, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8451137079999853, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.8451137079999853 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 247.98048966299973, |
|
"count": 90, |
|
"is_parallel": true, |
|
"self": 78.75213094899846, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 169.22835871400127, |
|
"count": 9174, |
|
"is_parallel": true, |
|
"self": 169.22835871400127 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14359048800008622, |
|
"count": 1, |
|
"self": 0.0010679340000478987, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.14252255400003833, |
|
"count": 1, |
|
"self": 0.14252255400003833 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |